INDEX

Explanations

download files and information

This neuron detects common English word‐ending fragments (like “ly,” “ive,” “ion,” etc.) that mark inflected or derived forms.

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

Negative Logits

and

-2.63

Koordin

-1.89

Kamera

-1.77

حوال

-1.72

 rudimentary

-1.70

明顯

-1.67

していました

-1.66

Ekster

-1.66

 alkoholu

-1.65

There

-1.63

POSITIVE LOGITS

 your

2.20

!!!!!!!

1.88

of

1.78

 also

1.72

!!!!!!

1.66

也

1.64

сында

1.63

1.58

the

1.57

 this

1.57

Activations Density 0.046%